Developing a CT-image-based clinical marker to predict vasospasm for aneurysmal subarachnoid hemorrhage patients

Abstract

Vasospasm is a common complication in aneurysmal subarachnoid hemorrhage (aSAH). Currently, patients with aSAH are usually monitored at intensive care unit (ICU) for approximately 14 days for early detection and treatment of vasospasm. To facilitate the diagnosis and decision-making process, this investigation aims to combine radiomics and deep learning technologies to predict vasospasm that requires intra-arterial treatment for patients with aSAH. For this purpose, a retrospective dataset was collected, containing a total of 52 aSAH patients. Next, a total of 1032 radiomic features and 768 vision transformer (ViT) based features were computed for each case to comprehensively quantify the aSAH characteristics. Based on the initial feature pool, analysis of variance (ANOVA) F1 score was applied to select 30 best performed features as the optimal feature cluster. Finally, a support vector machine (SVM) based classifier was trained to predict the vasospasm, and the model performance was evaluated using a 4-fold cross-validation strategy. Receiver operating characteristics (ROC) curve and confusion matrix were adopted as the assessing indices. The result show that the model achieved an area under the ROC curve (AUC) of 0.86±0.03, positive predictive value of 78%, negative predictive value of 76%, and overall accuracy of 77%, respectively. This investigation initially verified the feasibility of using CT images to accurately predict cerebral vasospasm.